Where the Model Changes Its Mind: Hindsight-Divergence Localization for Efficient Reinforcement Learning with Verifiable Rewards
cs.LG
Submitted: 2026-09-29
Updated: 2026-09-29
Code: https://github.com/THUDM/slime
Terminology
Sources
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning
- Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry
- Branching Policy Optimization: Sandbox-Native Language Agent Reinforcement Learning
- OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
- DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning
- Maximizing Rollout Informativeness under a Fixed Budget: A Submodular View of Tree Search for Tool-Use Agentic Reinforcement Learning
- Reinforcement Learning via Self-Distillation
- LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code
- Kimi k1.5: Scaling Reinforcement Learning with LLMs
- Tulu 3: Pushing Frontiers in Open Language Model Post-Training
- Solving Quantitative Reasoning Problems with Language Models
- Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing
- Localizing Credit at the Divergence: Path-Conditioned Self-Distillation for LLM Reasoning
- rStar-Coder: Scaling Competitive Code Reasoning with a Large-Scale Verified Dataset
- Understanding R1-Zero-Like Training: A Critical Perspective
- SD-Search: On-Policy Hindsight Self-Distillation for Search-Augmented Reasoning
- Llama-Nemotron: Efficient Reasoning Models
- Qwen3 Technical Report
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks